mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-07-29 01:15:59 +00:00
fa496c0c8d
* feat(browser): add agentic browser control
* fix(frontend): format browser view changes
* fix(browser): keep browser optional and isolate sidecar layout
* fix(browser): address PR review security and IME findings
- Nginx: add a browser-stream WebSocket location before the generic
/api/threads regex so Live upgrades instead of downgrading to HTTP
(both nginx.conf and nginx.local.conf).
- Ownership: require an existing owned thread for the WS stream and REST
navigate, and tear down the browser session on thread deletion so a
later caller cannot reuse a retained page/cookies by guessing the id.
- SSRF: enforce the URL policy at the browser request boundary via a
context-level route guard covering redirects, popups, iframes, and
subresources (skipped for CDP-attached Chrome).
- IME: skip key forwarding while a composition is active so confirming a
CJK candidate with Enter no longer submits the remote page form.
Adds regression tests for the request guard, session teardown on delete,
and the composing-Enter key decision.
* fix(frontend): smooth streaming in long tool threads
* Revert "fix(frontend): smooth streaming in long tool threads"
This reverts commit f0462516eabe77f138d4027ea1c714fb226683cf.
* fix(browser): address review security and lifecycle findings
- Reject cross-origin WebSocket upgrades on the live browser stream
(Origin allow-list reuse of CORS/same-origin helpers) to close a
WS-CSRF hole, and fail closed when the ownership store is absent.
- Warn when a CDP-attached session runs with the SSRF request guard
off, and drop the unreachable CDP screencast teardown dead code.
- Read browser session launch config from a single canonical source
(browser_navigate) so it is deterministic regardless of call order.
- Bound per-thread Chromium accumulation with idle-timeout eviction
and an LRU max-sessions cap.
- Reset the Live reconnect counter on a successful open so the stream
can't permanently stall after the cumulative attempt cap.
* fix(frontend): reduce long tool thread render stalls
Reuse stable historical message groups during streaming, defer heavy Markdown and browser previews, and lazy-decode message images.
* fix(browser): keep live control responsive during continuous input
Why: Manual browser control felt laggy — a physical click ran the remote
Playwright click three times and each non-move input synchronously awaited a
JPEG screenshot, so events queued behind capture (queue wait up to ~237ms).
The first async attempt used a trailing-edge debounce, which froze the visible
page until a wheel/keyboard gesture stopped ("scroll finishes, then it jumps").
What:
- Frontend forwards one `click` per physical click instead of also emitting
`down`/`up`, so the remote page is not clicked twice per gesture.
- Backend detaches live-frame capture from input dispatch: non-move actions
start a rate-limited background refresh loop (leading frame + bounded cadence)
that keeps emitting frames while input continues and never blocks dispatch.
- Add regression tests: input dispatch no longer awaits the screenshot, rapid
inputs coalesce, and continuous input keeps refreshing before it stops.
Scenarios: Verified in the live Browser panel — a single click completes in
~57ms (was blocked behind a 171ms capture), and a 1.14s sustained wheel gesture
renders ~7 frames throughout the scroll instead of one frame after it ends.
* fix(browser): harden worker and session lifecycle
* fix(browser): address latest review feedback
* fix(frontend): preserve optimistic new-chat message
* test(e2e): preserve mocked message run ids
* fix(browser): address capability review feedback
---------
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
72 lines
1.9 KiB
TypeScript
72 lines
1.9 KiB
TypeScript
import { describe, expect, it } from "@rstest/core";
|
|
|
|
import { decideBrowserKeyInput } from "@/components/workspace/browser-view/keyboard";
|
|
|
|
function ctx(
|
|
overrides: Partial<Parameters<typeof decideBrowserKeyInput>[0]> = {},
|
|
) {
|
|
return {
|
|
live: true,
|
|
editableTarget: false,
|
|
composing: false,
|
|
key: "a",
|
|
metaKey: false,
|
|
ctrlKey: false,
|
|
...overrides,
|
|
};
|
|
}
|
|
|
|
describe("decideBrowserKeyInput", () => {
|
|
it("forwards printable chars as text", () => {
|
|
expect(decideBrowserKeyInput(ctx({ key: "a" }))).toEqual({
|
|
type: "text",
|
|
text: "a",
|
|
});
|
|
});
|
|
|
|
it("forwards named keys as key presses", () => {
|
|
expect(decideBrowserKeyInput(ctx({ key: "Enter" }))).toEqual({
|
|
type: "key",
|
|
key: "Enter",
|
|
});
|
|
expect(decideBrowserKeyInput(ctx({ key: "ArrowLeft" }))).toEqual({
|
|
type: "key",
|
|
key: "ArrowLeft",
|
|
});
|
|
});
|
|
|
|
it("forwards modifier combos as a normalized key chord", () => {
|
|
expect(decideBrowserKeyInput(ctx({ key: "c", metaKey: true }))).toEqual({
|
|
type: "key",
|
|
key: "Meta+C",
|
|
});
|
|
expect(decideBrowserKeyInput(ctx({ key: "a", ctrlKey: true }))).toEqual({
|
|
type: "key",
|
|
key: "Control+A",
|
|
});
|
|
});
|
|
|
|
it("does not forward while an IME composition is active", () => {
|
|
// A CJK candidate confirmed with Enter must not submit the remote page.
|
|
expect(
|
|
decideBrowserKeyInput(ctx({ key: "Enter", composing: true })),
|
|
).toBeNull();
|
|
expect(
|
|
decideBrowserKeyInput(ctx({ key: "a", composing: true })),
|
|
).toBeNull();
|
|
});
|
|
|
|
it("ignores keys when not live or focus is on an editable target", () => {
|
|
expect(
|
|
decideBrowserKeyInput(ctx({ key: "Enter", live: false })),
|
|
).toBeNull();
|
|
expect(
|
|
decideBrowserKeyInput(ctx({ key: "Enter", editableTarget: true })),
|
|
).toBeNull();
|
|
});
|
|
|
|
it("ignores unmapped named keys", () => {
|
|
expect(decideBrowserKeyInput(ctx({ key: "F5" }))).toBeNull();
|
|
});
|
|
});
|